HEXAGONbeta

Binary Regression for BV Class Conditional Probability

A mix of human-written and AI-generated textHuman understanding: some partsstat.TH — Statistics Theorymath.ST — Statistics Theory

Contributed by Rajesh Dachiraju ↗

Version 1 / Oct 08, 2026 / CC BY 4.0

Abstract

In this article we solve the problem of binary regression when the class conditional probability is a multivariate function of bounded variation. We study the consistency of binary regression under a nonparametric sampling framework. Sufficient conditions are established for the convergence of the binary regression estimator, and quantitative error estimates are obtained. We further strengthen the analysis by introducing the assumption that the feature vectors possess a point density measure of bounded variation. Under this geometric regularity assumption, the expectation-based error estimate is replaced by a deterministic estimate, yielding deterministic convergence in the L2L^{2} norm and, consequently, almost sure convergence. The analysis demonstrates that the geometric distribution of the sampling points plays a fundamental role in the approximation properties of the estimator. Although the analysis is carried out on the torus Tm\mathbb{T}^{m}, the results extend to arbitrary bounded Lipschitz domains after affine scaling, embedding into Tm\mathbb{T}^{m}, and zero extension. The point density measure framework provides a deterministic geometric perspective on binary regression and establishes a connection between sampling geometry, bounded variation, and convergence theory.

Provenance statement

The theorem on deterministic convergence. This is generated using the help of ChatGPT.

References

  1. Rajesh Dachiraju. Approximation of a Multivariate Function of Bounded Variation from its Scattered Data. 2025arXiv
  2. Rajesh Dachiraju. Point Density Measures: A Measure-Theoretic Framework with Applications to Geometric Probability. Preprint. 2026. Submitted
  3. Devroye, Luc; Györfi, László; Lugosi, Gábor. A Probablistic Theory of Pattern Recognition. NewYork: Springer Verlag, vol. 31. 1996DOI
  4. Evans, L.C.; American Mathematical Society. Partial Differential Equations. American Mathematical Society. 1998link
  5. Iosif Pinelis (https://mathoverflow.net/users/36721/iosif-pinelis). A problem on rate of decay of fill distance?. URL:https://mathoverflow.net/q/391340 (version: 2021-05-20)link
  6. Kuipers, Lauwerens; Niederreiter, Harald. Uniform distribution of sequences. Courier Corporation. 2012
  7. Scholkopf, Bernhard; Smola, Alexander J. Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond. MIT Press. 2001
  8. Zheng, Weiying; Qi, He. On Friedrichs–Poincaré-type inequalities. Journal of mathematical analysis and applications, vol. 304, no. 2, pp. 542–551. 2005

Version history

  1. v1Submitted by Rajesh DachirajuInitial depositCurrentOct 08, 2026